Decide

Generate a Decision Record through structured analysis pipeline. Use when comparing architectural options, choosing between technical approaches, evaluating build-vs-buy trade-offs, or making any design decision that needs evidence-based scoring.

9 stars 4 forksOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add deejay-hub/salesforce-ada-agent-skills --skill decide
Manual install
git clone --depth 1 https://github.com/deejay-hub/salesforce-ada-agent-skills.git /tmp/salesforce-ada-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/salesforce-ada-agent-skills/.claude/skills/decide ~/.claude/skills/decide

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

You are in DECIDE mode. Guide the user through a structured decision pipeline for "$ARGUMENTS".

## Pipeline

Execute these steps IN ORDER. Pause for user input between each step. Do not skip steps.

### Step 1: Discovery

Gather context using `AskUserQuestion`. Ask about:
- Business problem or technical challenge
- Key numbers (record volumes, user count, transaction frequency)
- Salesforce products, editions, and existing customizations
- Delivery timeline
- Budget, compliance, or technical constraints

Skip questions already answered in "$ARGUMENTS". Do NOT search documentation during discovery.

If the topic involves Agentforce, autonomous agents, LLM-driven actions, MCP/A2A agent integrations, or agentic vs. traditional automation, read `knowledge/modifiers/agentic-enterprise-lens.md`, state that the Agentic Enterprise lens is active, and include its mandatory discovery questions (e.g., does the agent assist or act, which actions require human approval).

**Limit discovery to 2 rounds of questions (max 8 questions total).** If critical context is still missing after Step 1, gather it in Step 4's differentiating questions instead.

### Step 2: Solution Options

#### 2a. Research

First, check whether an Architect Decision Guide (listed in the system prompt, or at https://architect.salesforce.com/decision-guides) covers this decision. If one does, fetch it and use its options and trade-off dimensions as the starting point.
Read the full skill on GitHub

Details

Skill name
decide
Path
.claude/skills/decide/SKILL.md
License
MIT
Repo updated
15 October 2026

FAQ

What does the Decide skill do?

Generate a Decision Record through structured analysis pipeline. Use when comparing architectural options, choosing between technical approaches, evaluating build-vs-buy trade-offs, or making any design decision that needs evidence-based scoring.

How do I install the Decide skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add deejay-hub/salesforce-ada-agent-skills --skill decide. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Decide popular?

It lives in deejay-hub/salesforce-ada-agent-skills, which has 9 GitHub stars and 4 forks.

Related skills

Learn

9

deejay-hub/salesforce-ada-agent-skills

Educate on Salesforce architecture topics with structured, citation-grounded responses. Use when the user wants to understand a concept, pattern, feature, or best practice.

Learning & Education

Storm Deepresearch

9

keyelifeai/keye-open-skills

用多视角扫描、矛盾图、证据搜索和自我复核组织研究简报。用户要求深度研究、多视角分析、研究争议、形成决策材料或使用 storm-deepresearch 时使用。

Other

Spectacles 522 to 515 Migration

9

PtPavloTkachenko/spectacles-agent-skills

Battle-tested playbook for migrating a Lens Studio 5.22 project down to LS 5.15.4 for Spectacles (2024). Triggers on: migrate 5.22 to 5.15, downgrade lens studio project, 5.22 package errors in 5.15, SingleCompressionSettings error, PerformanceCompressionSettings error, Invalid graph header, !passList.empty(), duplicate PassInfo reimport loop, PassInfo transplant, materials white after clone, 5.22 lspkg crashes 5.15.

Other

Proposal Assembler

10

gener8v/gener8v.claude-skills.rfp-response

Assembles all reviewed, validated sections into a single proposal-final.md. Inserts front matter, enforces section order, attaches appendices, performs a final compliance pre-flight, and surfaces any unresolved issues. Trigger when the user says "assemble the proposal," "build the final document," "put it together," or after the compliance validator has produced compliance-report.md. Will refuse to assemble if critical compliance failures exist.

Other

Funded Phd Dossier

9

chinnkirsten/funded-phd-dossier

为社会科学博士申请者检索、查证并匹配全球全额资助的研究型博士项目。根据申请者的专业背景、研究兴趣、语言成绩、国籍或居留身份和目标入学季,核对 PhD、DPhil、项目制 studentship 与带薪博士职位的资助承诺、资格门槛、申请材料和截止日期,并形成可执行、可追溯的候选清单。用户想找全奖博士、判断某个项目是否真正全奖、评估个人资格、比较资助路径,或为一个学科和一批申请者建立持续更新的项目库时使用。

Other

Requirements Mapper

10

gener8v/gener8v.claude-skills.rfp-response

Maps every explicit and implicit RFP requirement to available evidence from the collateral brief. Produces a coverage matrix so downstream skills know where to ground claims, where to assert, and where to acknowledge gaps. Trigger when the user says "map the requirements," "build the coverage matrix," "what can we substantiate," or after the collateral analyzer has produced brief.md and gap-report.md.

Other

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.